CVE-2026-27940
Fixed in a distro release EPSS <1%CVSS 7.8
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.
Products: ggml-org llama.cpp
Distro releases
| Release | Package | Fixed in |
|---|---|---|
| Debian 14 | llama.cpp | 8461+dfsg-1 |
| Ubuntu 25.10 | llama.cpp | no fix |
| Ubuntu 26.04 LTS | llama.cpp | no fix |
| Ubuntu 26.10 | llama.cpp | no fix |